Instructions to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2

Run Hermes

hermes

Qwen3.6-27B MTPLX Optimized Speed V2

The recommended 27B model for local coding and agent work with MTPLX on Apple Silicon.

V2 is a hand-calibrated quantization of Qwen3.6-27B built for one job: fast, high-quality coding on a Mac. It cuts quantization loss by 47% compared to the original Optimized Speed release, and it pulls further ahead the longer an agent session runs.

Quickstart

brew install youssofal/mtplx/mtplx
mtplx start

mtplx start recommends this model automatically on Macs with 32 GB of unified memory or more, and offers smaller verified models below that.

Direct usage:

mtplx pull Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2
mtplx run "hello" --model Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2
mtplx serve --model Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2 --port 8000

mtplx serve exposes OpenAI and Anthropic compatible endpoints, so the model works inside OpenCode, Claude Code, Cline, and other coding agents.

The numbers

Measured on an M5 Max against the original Optimized Speed release, same engine, same prompts:

KL divergence to the full-precision bf16 model: 0.072 vs 0.135, on an 86k-token held-out battery. 47% less quantization loss than the original.
Draft acceptance at 17k tokens of agent context: 98 / 86 / 78% per draft position, vs 73 / 50 / 33% for the original.
Decode at that context: 45.7 vs 36.1 tok/s, about 27% faster.
Peak speculative multiplier: 2.86x over the matched autoregressive baseline, the highest we have measured on any 27B build.

These numbers are one story, not four. Speculative decoding is only as fast as its drafts are accurate, and a trunk that stays this close to full precision keeps its drafts landing deep into long contexts. Quality is the speed lever.

The tradeoff: V2 is 19.9 GB vs 16.4 GB for the original, so cold short chats can be a few percent slower. Everything else is faster.

How it is built

Not a round-to-nearest conversion. The layout was tuned tensor by tensor against the bf16 reference:

Most weights are 4-bit with small groups, refit against real activation statistics with error-weighted least squares instead of naive rounding.
The tensors that hurt most at 4-bit were promoted by hand: embeddings, the output head, convolution and attention output projections, and the late MLP layers run at 8-bit, with the most sensitive layers kept in full bf16.
The native multi-token-prediction head ships as a calibrated sidecar (mtp/weights.safetensors). No external draft model is needed.

The result lands at roughly 5.8 bits per weight. The goal was never the smallest file. It is the best coding model that still fits comfortably in unified memory.

About MTPLX

MTPLX is an MLX-native inference engine built around Qwen's native multi-token prediction: the model drafts its own tokens and the engine verifies them with exact probability-ratio acceptance, so output quality matches non-speculative decoding at any temperature. It adds warm session caching for fast agent round-trips, a native macOS app, and a one-line install via Homebrew or pip install mtplx.

Which model to pick

Coding, tool use, long agent sessions: this model.
Tight on storage, mostly short chat: Qwen3.6-27B-MTPLX-Optimized-Speed is 3.5 GB smaller.
Lower-memory Macs: Qwen3.5-9B and Qwen3.5-4B are verified for smaller memory tiers.

Verification

mtplx_runtime.json records the verified runtime contract:

architecture: qwen3-next-mtp, maximum MTP depth 3, turbo profile
sampler: temperature 0.6, top-p 0.95, top-k 20
KLD and perplexity measured against the bf16 teacher on an 86k-token held-out battery
verified hardware: Apple M5 Max, 128 GB unified memory
served model id: mtplx-qwen36-27b-optimized-speed-v2

Files

model-*.safetensors: calibrated hybrid-quantized model shards
mtp/weights.safetensors: native MTP sidecar
mtplx_runtime.json: verified MTPLX runtime contract
tokenizer and processor files from the Qwen model family

Sources and attribution

Component	Source	License
Base model	Qwen/Qwen3.6-27B	Apache-2.0
MTPLX conversion, calibration, and runtime contract	youssofal/MTPLX	Apache-2.0

Downloads last month: 408

Safetensors

Model size

27B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit

Model tree for Youssofal/Qwen3.6-27B-MTPLX-Optimized-Speed-V2

Base model

Qwen/Qwen3.6-27B

Quantized

(680)

this model